Added
- Add
prompts.render(ref, vars?)toworkflowScriptfor explicitly scoped package, user, and project prompt fragments with simple{{name}}interpolation (#960). - Expose a versioned
pi-subagents/project-panesTypeScript API so other Pi extensions can deterministically open, inspect, and close project-owned Herdr panes without invoking the model-facingsubagenttool. The structured status includes bounded pane runtime state and an opt-in idle-only close guard; Pi project trust remains an explicit human verification step. Thanks to @wiizard-chen for #949. - Preserve short-lived completion replay records and bounded output archives so waits can recover consumed async result details after watcher delivery or restart.
- Add
subagent({ action: "guide" })and/subagents-guide [topic]to read current-version packaged guides. - Persist workflow child attempts, status heartbeats, session paths, and artifacts in their enclosing mission, and add explicit mission decision resolution.
Fixed
- Make live foreground workflow children visible as workflow-owned Fleet rows, route Herdr inspection to their workflow parent, and report their active and needs-attention state to Herdr. Thanks to @lukechen526 for #965.
- Wait for retained-child resumes inside
workflowScriptto finish and return completed output before the script continues (#961). - Keep fork-context workflow children inside their managed worktree by aligning the persisted child session cwd before launch. Thanks to @flopsi for #953.
- Show the resolved child agent in async workflow status while keeping the workflow key as its stable label. Thanks to @albertgwo for #955.
- Reject workflow scripts that finish with unawaited child launches and name every launch that was aborted. Thanks to @zig-zag-zig for #957.
- Reject mismatched completion replay archive paths so stale replay cleanup cannot delete another run's saved output archive.
- Keep
git-rootproject agent and package discovery stable when incidental.pistate appears in a nested linked worktree. Thanks to @klajdo-f for #950. - Read skill descriptions from YAML block scalars instead of exposing their markers. Thanks to @ashlineldridge for #945.
- Collapse repeated subagent status snapshots in live widgets so status polling does not overflow the chat.
- Give invalid
subagentactions safe next steps and typo suggestions without suggesting destructive actions for ambiguous input. - Let the Fleet inspector use extension-local keybindings for terminals that intercept navigation keys. Thanks to @epheien for #940.
- Restore completed foreground children from a compact Fleet history index after session resume. Thanks to @epheien for #946.
- Compact noisy repeated subagent live-output lines and bound workflow live-card rows so progress stays readable in the TUI (#947).